Tag
15 articles
Explore how deepDoctection enables the construction of end-to-end document intelligence pipelines by integrating layout analysis, OCR, and table extraction, with support for custom NER services and RAG workflows.
Learn how Pixel-Native RAG treats documents as visual images to improve retrieval accuracy and support complex document understanding tasks.
A roundup of 10 open-source no-code AI platforms that simplify the creation of LLM apps, RAG systems, and AI agents using visual and plain-English tools.
This article explains the RAG-Anything framework, a multimodal extension of Retrieval-Augmented Generation that retrieves and integrates information across text, tables, equations, and images.
Mistral AI's Mistral OCR 4 introduces citation-ready, structured document outputs that enhance RAG, agentic, and enterprise search pipelines. The model supports 170 languages and runs in a single self-hosted container.
Explore Crawlee for Python, a powerful web crawling framework designed for building scalable data pipelines that support AI applications like RAG. Learn how it handles JavaScript rendering, link graphs, and data export.
This explainer introduces the Open Knowledge Format (OKF), a vendor-neutral specification for structuring knowledge for AI agents. It explains how OKF uses Markdown and YAML to create curated knowledge bundles, distinguishing it from traditional RAG systems.
Turbovec, a new Rust-based vector index built on Google's TurboQuant algorithm, offers 16x compression and zero codebook training for RAG pipelines.
Vector databases are becoming essential for RAG and agentic AI systems. A new analysis compares nine leading platforms on architecture, pricing, and scalability.
Learn how PageIndex is revolutionizing information retrieval in AI by using reasoning instead of traditional vector-based methods, making AI systems smarter and more accurate.
This article explains the advanced AI concepts behind Qwen 3.6-35B-A3B, a multimodal model that combines MoE routing, RAG, and session persistence for intelligent, context-aware AI applications.
This article explains how Microsoft's Phi-4-Mini AI model uses quantization, RAG, and LoRA techniques to create efficient, powerful language models that can answer questions and use tools.